Backtest History
285 graded games
Every graded prediction from the frozen walk-forward backtest, next to the closing spread and the final margin. Lines are quoted for the home team.
| Season | Wk | Matchup | Score | Model | Close | Result | Model err |
|---|---|---|---|---|---|---|---|
| 2023 | 16 | DAL @ MIA | 20–22 | -2.1 | -1.5 | -2.0 | 0.1 (model closer than the closing line) |
| 2023 | 16 | DET @ MIN | 30–24 | -1.4 | +2.5 | +6.0 | 7.4 |
| 2023 | 16 | GB @ CAR | 33–30 | +5.9 | +3.5 | +3.0 | 2.9 |
| 2023 | 16 | IND @ ATL | 10–29 | -2.1 | -3.0 | -19.0 | 16.9 |
| 2023 | 16 | JAX @ TB | 12–30 | -0.3 | +2.0 | -18.0 | 17.7 (model closer than the closing line) |
| 2023 | 16 | LV @ KC | 20–14 | -8.8 | -11.0 | +6.0 | 14.8 (model closer than the closing line) |
| 2023 | 16 | NE @ DEN | 26–23 | -6.2 | -7.0 | +3.0 | 9.2 (model closer than the closing line) |
| 2023 | 16 | NO @ LA | 22–30 | -2.7 | -4.0 | -8.0 | 5.3 |
| 2023 | 16 | NYG @ PHI | 25–33 | -13.8 | -14.0 | -8.0 | 5.8 (model closer than the closing line) |
| 2023 | 16 | SEA @ TEN | 20–17 | +2.0 | +3.0 | +3.0 | 1.0 |
| 2023 | 16 | WAS @ NYJ | 28–30 | -5.1 | -3.0 | -2.0 | 3.1 |
| 2023 | 15 | ATL @ CAR | 7–9 | +4.9 | +3.0 | -2.0 | 6.9 |
| 2023 | 15 | BAL @ JAX | 23–7 | +4.8 | +4.0 | +16.0 | 11.2 (model closer than the closing line) |
| 2023 | 15 | CHI @ CLE | 17–20 | -2.8 | -3.0 | -3.0 | 0.2 |
| 2023 | 15 | DAL @ BUF | 10–31 | +2.3 | -2.0 | -21.0 | 23.3 |
| 2023 | 15 | DEN @ DET | 17–42 | -1.4 | -5.5 | -25.0 | 23.6 |
| 2023 | 15 | HOU @ TEN | 19–16 | -5.2 | -3.0 | +3.0 | 8.2 |
| 2023 | 15 | KC @ NE | 27–17 | +7.6 | +10.0 | +10.0 | 2.4 |
| 2023 | 15 | LAC @ LV | 21–63 | -1.3 | -3.0 | -42.0 | 40.7 |
| 2023 | 15 | MIN @ CIN | 24–27 | -1.4 | -3.0 | -3.0 | 1.6 |
| 2023 | 15 | NYG @ NO | 6–24 | -6.3 | -6.0 | -18.0 | 11.7 (model closer than the closing line) |
| 2023 | 15 | NYJ @ MIA | 0–30 | -8.1 | -7.5 | -30.0 | 21.9 (model closer than the closing line) |
| 2023 | 15 | PHI @ SEA | 17–20 | +3.4 | +5.0 | -3.0 | 6.4 (model closer than the closing line) |
| 2023 | 15 | PIT @ IND | 13–30 | -0.7 | -1.5 | -17.0 | 16.3 |
| 2023 | 15 | SF @ ARI | 45–29 | +15.3 | +12.5 | +16.0 | 0.7 (model closer than the closing line) |
| 2023 | 15 | TB @ GB | 34–20 | -6.3 | -4.0 | +14.0 | 20.3 |
| 2023 | 15 | WAS @ LA | 20–28 | -9.1 | -6.5 | -8.0 | 1.1 (model closer than the closing line) |
| 2023 | 14 | BUF @ KC | 20–17 | -1.0 | -2.0 | +3.0 | 4.0 (model closer than the closing line) |
| 2023 | 14 | CAR @ NO | 6–28 | -7.8 | -5.5 | -22.0 | 14.2 (model closer than the closing line) |
| 2023 | 14 | DEN @ LAC | 24–7 | -1.4 | -3.0 | +17.0 | 18.4 (model closer than the closing line) |
| 2023 | 14 | DET @ CHI | 13–28 | +1.3 | +3.0 | -15.0 | 16.3 (model closer than the closing line) |
| 2023 | 14 | GB @ NYG | 22–24 | +9.8 | +6.0 | -2.0 | 11.8 |
| 2023 | 14 | HOU @ NYJ | 6–30 | +4.6 | +3.5 | -24.0 | 28.6 |
| 2023 | 14 | IND @ CIN | 14–34 | -4.7 | -3.0 | -20.0 | 15.3 (model closer than the closing line) |
| 2023 | 14 | JAX @ CLE | 27–31 | -0.5 | -2.5 | -4.0 | 3.5 |
| 2023 | 14 | LA @ BAL | 31–37 | -8.6 | -7.5 | -6.0 | 2.6 |
| 2023 | 14 | MIN @ LV | 3–0 | +2.2 | +3.0 | +3.0 | 0.8 |
| 2023 | 14 | NE @ PIT | 21–18 | -8.0 | -6.0 | +3.0 | 11.0 |
| 2023 | 14 | PHI @ DAL | 13–33 | -6.9 | -3.5 | -20.0 | 13.1 (model closer than the closing line) |
| 2023 | 14 | SEA @ SF | 16–28 | -15.7 | -14.5 | -12.0 | 3.7 |
| 2023 | 14 | TB @ ATL | 29–25 | -2.2 | -1.5 | +4.0 | 6.2 |
| 2023 | 14 | TEN @ MIA | 28–27 | -14.3 | -14.0 | +1.0 | 15.3 |
| 2023 | 13 | ARI @ PIT | 24–10 | -9.6 | -6.0 | +14.0 | 23.6 |
| 2023 | 13 | ATL @ NYJ | 13–8 | +1.3 | +2.0 | +5.0 | 3.7 |
| 2023 | 13 | CAR @ TB | 18–21 | -6.3 | -4.0 | -3.0 | 3.3 |
| 2023 | 13 | CIN @ JAX | 34–31 | -9.3 | -10.0 | +3.0 | 12.3 (model closer than the closing line) |
| 2023 | 13 | CLE @ LA | 19–36 | -1.3 | -3.5 | -17.0 | 15.7 |
| 2023 | 13 | DEN @ HOU | 17–22 | -2.4 | -3.5 | -5.0 | 2.6 |
| 2023 | 13 | DET @ NO | 33–28 | -0.0 | +4.0 | +5.0 | 5.0 |
| 2023 | 13 | IND @ TEN | 31–28 | +1.3 | +1.5 | +3.0 | 1.7 |
Model and Close are home lines; Result is the final margin on the same axis. Model err is the absolute miss of the model's margin, shown green when the model was closer than the closing line.